SOURCE-LINKED INTELLIGENCE

Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Android agents using a hybrid action space that combines GUI actions and tool actions (e.g., accessing application data via APIs) remain largely underexplored, mainly due to the excessive effort required to create tools. To address this gap, we introduce DroidTool, a framework for augmenting the agents with self-generated tools, which are realized as Python functions operating on application states (e.g., a database). To create tools with minimal human labor, DroidTool employs an agentic workflow featuring stages: proposal, implementation, test generation and execution, and repair. Notably, wh

Read original source ↗ Open in workspace

recordType

paper

region

Global